© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92135
    Prev
    Next
    INDEX
    Explanations

    sneaker brands

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of sneaker and athletic shoe brands and model names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vaadin
    -0.89
     брюки
    -0.84
     Table
    -0.81
     through
    -0.79
    tigen
    -0.77
    setContent
    -0.75
     Sleeves
    -0.73
     Blouse
    -0.73
    gwt
    -0.73
    cplusplus
    -0.72
    POSITIVE LOGITS
     Nike
    1.69
     sneaker
    1.60
     sneakers
    1.58
    Nike
    1.51
     Adidas
    1.34
     trainers
    1.23
     basketball
    1.18
     trainer
    1.14
    Sne
    1.14
     adidas
    1.13
    Activations Density 0.013%

    No Known Activations